add api as proxy

api_server.py

@@ -111,7 +111,7 @@ async def detokenize(request: DetokenizeRequest):
         return JSONResponse(content=generator.model_dump())
 
 
-@router.get("/v1/models")
+@router.get("/api/v1/models")
 async def show_available_models():
     models = await openai_serving_completion.show_available_models()
     return JSONResponse(content=models.model_dump())
@@ -123,7 +123,7 @@ async def show_version():
     return JSONResponse(content=ver)
 
 
-@router.post("/v1/chat/completions")
+@router.post("/api/v1/chat/completions")
 async def create_chat_completion(request: ChatCompletionRequest,
                                  raw_request: Request):
     generator = await openai_serving_chat.create_chat_completion(
@@ -139,7 +139,7 @@ async def create_chat_completion(request: ChatCompletionRequest,
         return JSONResponse(content=generator.model_dump())
 
 
-@router.post("/v1/completions")
+@router.post("/api/v1/completions")
 async def create_completion(request: CompletionRequest, raw_request: Request):
     generator = await openai_serving_completion.create_completion(
         request, raw_request)
@@ -153,7 +153,7 @@ async def create_completion(request: CompletionRequest, raw_request: Request):
         return JSONResponse(content=generator.model_dump())
 
 
-@router.post("/v1/embeddings")
+@router.post("/api/v1/embeddings")
 async def create_embedding(request: EmbeddingRequest, raw_request: Request):
     generator = await openai_serving_embedding.create_embedding(
         request, raw_request)